{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PJZNURSGW57Z7SI7CK6T46VIUQ","short_pith_number":"pith:PJZNURSG","canonical_record":{"source":{"id":"1812.09028","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-21T10:17:29Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"a2289ed2b4ac348d3e5e2e16e87dc5dc210c013fd0bd22f77aff829acca90d23","abstract_canon_sha256":"b5d2ff2893779db1f7ec3c2a4d058296f965a2e7e19b763a7901caf79a4c31a4"},"schema_version":"1.0"},"canonical_sha256":"7a72da4646b77f9fc91f12bd3e7aa8a425c05869228ab85efd4bf9a94bf3336a","source":{"kind":"arxiv","id":"1812.09028","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.09028","created_at":"2026-05-17T23:57:30Z"},{"alias_kind":"arxiv_version","alias_value":"1812.09028v2","created_at":"2026-05-17T23:57:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09028","created_at":"2026-05-17T23:57:30Z"},{"alias_kind":"pith_short_12","alias_value":"PJZNURSGW57Z","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PJZNURSGW57Z7SI7","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PJZNURSG","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PJZNURSGW57Z7SI7CK6T46VIUQ","target":"record","payload":{"canonical_record":{"source":{"id":"1812.09028","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-21T10:17:29Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"a2289ed2b4ac348d3e5e2e16e87dc5dc210c013fd0bd22f77aff829acca90d23","abstract_canon_sha256":"b5d2ff2893779db1f7ec3c2a4d058296f965a2e7e19b763a7901caf79a4c31a4"},"schema_version":"1.0"},"canonical_sha256":"7a72da4646b77f9fc91f12bd3e7aa8a425c05869228ab85efd4bf9a94bf3336a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:30.412504Z","signature_b64":"G4AdAGrczdL7BI6T3A4lv5d/AKKTI76ps60OzShFyVSb0r/dcCnIJjvtuYZm2BoT4JokzKaI4V6HdQ2Z9/DnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a72da4646b77f9fc91f12bd3e7aa8a425c05869228ab85efd4bf9a94bf3336a","last_reissued_at":"2026-05-17T23:57:30.411909Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:30.411909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.09028","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"veiJMHhR/BHipA6+h6zVop9vUmaRDwcmAcn7Ze385NICPIcBWHOqlzSCr8RJu3uSui+nkd1bN1sj+ExC0lsmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T20:01:14.114434Z"},"content_sha256":"d6def21119c812adbf49f46e67c28efb5cd58d6b29e1af6b34382d0fa99a9ca9","schema_version":"1.0","event_id":"sha256:d6def21119c812adbf49f46e67c28efb5cd58d6b29e1af6b34382d0fa99a9ca9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PJZNURSGW57Z7SI7CK6T46VIUQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chunxiao Liu, Junning Huang, Lanxin Lei, Liang Lin, Sirui Xie, Wei Zhang, Zheng Ma","submitted_at":"2018-12-21T10:17:29Z","abstract_excerpt":"Reinforcement learning agents need exploratory behaviors to escape from local optima. These behaviors may include both immediate dithering perturbation and temporally consistent exploration. To achieve these, a stochastic policy model that is inherently consistent through a period of time is in desire, especially for tasks with either sparse rewards or long term information. In this work, we introduce a novel on-policy temporally consistent exploration strategy - Neural Adaptive Dropout Policy Exploration (NADPEx) - for deep reinforcement learning agents. Modeled as a global random variable fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09028","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+cdfegk5iPpxcm2ve7vpT9X+HGuSpJplmiW3HRTWdUHI48i2BZoOLviYuU47CEr8xqAD1wV7YLm+Pw2SSqOxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T20:01:14.115221Z"},"content_sha256":"c6d6ffeeafec1647dd6e9baa3fbb2f0adedecd559dc06e3e59545323b0956710","schema_version":"1.0","event_id":"sha256:c6d6ffeeafec1647dd6e9baa3fbb2f0adedecd559dc06e3e59545323b0956710"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJZNURSGW57Z7SI7CK6T46VIUQ/bundle.json","state_url":"https://pith.science/pith/PJZNURSGW57Z7SI7CK6T46VIUQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJZNURSGW57Z7SI7CK6T46VIUQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T20:01:14Z","links":{"resolver":"https://pith.science/pith/PJZNURSGW57Z7SI7CK6T46VIUQ","bundle":"https://pith.science/pith/PJZNURSGW57Z7SI7CK6T46VIUQ/bundle.json","state":"https://pith.science/pith/PJZNURSGW57Z7SI7CK6T46VIUQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJZNURSGW57Z7SI7CK6T46VIUQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PJZNURSGW57Z7SI7CK6T46VIUQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b5d2ff2893779db1f7ec3c2a4d058296f965a2e7e19b763a7901caf79a4c31a4","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-21T10:17:29Z","title_canon_sha256":"a2289ed2b4ac348d3e5e2e16e87dc5dc210c013fd0bd22f77aff829acca90d23"},"schema_version":"1.0","source":{"id":"1812.09028","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.09028","created_at":"2026-05-17T23:57:30Z"},{"alias_kind":"arxiv_version","alias_value":"1812.09028v2","created_at":"2026-05-17T23:57:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09028","created_at":"2026-05-17T23:57:30Z"},{"alias_kind":"pith_short_12","alias_value":"PJZNURSGW57Z","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PJZNURSGW57Z7SI7","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PJZNURSG","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:c6d6ffeeafec1647dd6e9baa3fbb2f0adedecd559dc06e3e59545323b0956710","target":"graph","created_at":"2026-05-17T23:57:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Reinforcement learning agents need exploratory behaviors to escape from local optima. These behaviors may include both immediate dithering perturbation and temporally consistent exploration. To achieve these, a stochastic policy model that is inherently consistent through a period of time is in desire, especially for tasks with either sparse rewards or long term information. In this work, we introduce a novel on-policy temporally consistent exploration strategy - Neural Adaptive Dropout Policy Exploration (NADPEx) - for deep reinforcement learning agents. Modeled as a global random variable fo","authors_text":"Chunxiao Liu, Junning Huang, Lanxin Lei, Liang Lin, Sirui Xie, Wei Zhang, Zheng Ma","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-21T10:17:29Z","title":"NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09028","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d6def21119c812adbf49f46e67c28efb5cd58d6b29e1af6b34382d0fa99a9ca9","target":"record","created_at":"2026-05-17T23:57:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b5d2ff2893779db1f7ec3c2a4d058296f965a2e7e19b763a7901caf79a4c31a4","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-21T10:17:29Z","title_canon_sha256":"a2289ed2b4ac348d3e5e2e16e87dc5dc210c013fd0bd22f77aff829acca90d23"},"schema_version":"1.0","source":{"id":"1812.09028","kind":"arxiv","version":2}},"canonical_sha256":"7a72da4646b77f9fc91f12bd3e7aa8a425c05869228ab85efd4bf9a94bf3336a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a72da4646b77f9fc91f12bd3e7aa8a425c05869228ab85efd4bf9a94bf3336a","first_computed_at":"2026-05-17T23:57:30.411909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:30.411909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G4AdAGrczdL7BI6T3A4lv5d/AKKTI76ps60OzShFyVSb0r/dcCnIJjvtuYZm2BoT4JokzKaI4V6HdQ2Z9/DnAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:30.412504Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.09028","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6def21119c812adbf49f46e67c28efb5cd58d6b29e1af6b34382d0fa99a9ca9","sha256:c6d6ffeeafec1647dd6e9baa3fbb2f0adedecd559dc06e3e59545323b0956710"],"state_sha256":"95b4576c5b88e13312b818bdc70a8ed690b37a1687d2880bd41fc01a9efa66b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yn5Xm2hy2noSc4Hi4OrBPPjya38JGjCowmopUdV9p+jyKgkOh2QbLsA7RGPLEAEd2av4VQ+7MCmboJF/yf/fAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T20:01:14.119448Z","bundle_sha256":"45d9cbe544c706d9a848714972e17a8b4973526ddfdb8d063336930d24b31907"}}